The Impact of Artificial Intelligence Technologies on Improving Physical Fitness Components Based on Physical and Physiological Conditions

Abstract

This study aims to improve an artificial intelligence (AI) model for training and nutritional analysis and recommendations determine vital indicators related to with fitness components, evaluate the model's effectiveness through a comparative study and establish an applied framework for coaches and specialists. The study employed an experimental approach, measuring the effect of the independent variable (the AI ​​system (K.A.I.N.)) on the relies on variables (fitness components and physiological indicators). The study population consisted of practitioners in clubs and advanced training centers. A purposive sample of 40 elite male and female athletes aged 18 to 25, was randomly separated into two equal groups: an experimental group (n=20) that received the K.A.I.N. system, and a control group (n=20) that followed the traditional program. A range of tools were used including the InBody body composition analyzer, Polar Vantage V smartwatches for monitoring physiological indicators and standardized physical tests. The results demonstrate a statistically significant advantage for the experimental group in all fitness components (explosive power, endurance, speed, and flexibility) and physiological indicators (recovery rate, HRV) compared to the control group with a very large effect size. The study concluded that the K.A.I.N. artificial intelligence system has a superior capacity  to develop fitness components and physiological performance in athletes compared to traditional approaches. It required integrating physiological monitoring tools into athletes' daily routines and implementing an interactive framework to adjust training loads based on objective data.